Our primary goal in machine learning is to predict a value based on input values, depending on the desired output we need to choose the correct cost function and correct neurons to be able to represent the final data correctly, this output values can have different forms of representations:

Discrete

When the output variable can be described or classified in groups then we can say that the variable is discrete, for example, our machine learning algorithm predicts weather tomorrow is going to rain or not, here our universe of choices is only reduced to two (yes or no)

Continous

When the output variable can have an infinite range of values we say the variable is continuous, for example, our machine learning algorithm predicts the temperature of tomorrow’s day, this value can be 10 degrees or 11 degrees or maybe 10.1 or 10.12 this range is infinite if you think about it.

When a machine learning algorithm outputs a discrete variable we say this algorithm tackles a classification problem.

When a machine learning algorithm outputs a continuous variable we say this algorithm tackles a regression problem.